© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 31750
    Prev
    Next
    INDEX
    Explanations

    it is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SCI
    -0.09
    æĸ½
    -0.09
    _CLK
    -0.09
    交ç»ĩ
    -0.09
    اÙĪÙĬ
    -0.08
    ÑĢÑıд
    -0.08
    æĪIJåŀĭ
    -0.08
    omid
    -0.08
    .jetbrains
    -0.08
    shit
    -0.08
    POSITIVE LOGITS
     themselves
    0.09
    éĹ¾
    0.09
    ãĥ³ãĥĪ
    0.08
    andin
    0.08
    FTA
    0.08
    iner
    0.08
     ÑģебÑı
    0.08
    ingu
    0.08
    andi
    0.08
    对该
    0.08
    Activations Density 0.181%

    No Known Activations